• Advance AI Safety: Design, implement, and evaluate attack and defense strategies for LLM jailbreaks (prompt injection, obfuscation, narrative red teaming) and deploy them as production-grade services. • Build Scalable Safety Infrastructure: Architect and deploy distributed safety evaluation pipelines handling millions of requests, with real-time monitoring, alerting, and incident response capabilities. • Large-Scale Data Engineering: Design ETL pipelines for processing terabytes of safety-related data (attack patterns, behavioral logs, model outputs); build data lakes and feature stores for safety ML systems. • Evaluate AI Behavior: Analyze and simulate human-AI interaction patterns at scale to uncover behavioral vulnerabilities, social engineering risks, and over-defensive vs. permissive response tradeoffs. • Agentic AI Security: Build production workflows for multi-agent safety (agent self-checks, regulatory compliance, defense chains) spanning perception, reasoning, and action. • MLOps & Model Deployment: Deploy safety models to production using containerized microservices, implement CI/CD pipelines for model updates, and manage model versioning and A/B testing infrastructure. • Benchmark & Harden LLMs: Create reproducible, automated evaluation protocols for safety, over-defensiveness, and adversarial resilience across diverse models with continuous integration.

• Collaborate with major clients and partners • Clearly explain technical concepts and propose solution recommendations in direct collaboration with major clients and partners. • Evaluate, monitor, and continuously improve the performance of our Retrieval-Augmented Generation (RAG) pipeline to ensure high-quality responses to legal queries. • Prototype, evaluate, and enhance our RAG pipeline to increase response accuracy, speed, and cost-efficiency. • Fine-tune large language models (LLMs) to ensure precision and relevance when answering legal questions. • Design, implement, and maintain robust ETL pipelines for seamless data transformation. • Optimize workflows for storing and managing parsed content in a vector database to enable efficient information retrieval. • Develop and improve embedding and chat models to optimize the user experience. • Work closely with the software engineering team to seamlessly integrate AI/ML components into the overall product architecture. • Deploy LLMs and associated models to production using Azure cloud infrastructure to ensure optimal performance and reliability. • Collaborate with the operations team to automate model deployments using Terraform and other CI/CD tools to ensure scalability and efficiency.

• AI Discovery & Solutioning: Understand energy customers' AI strategy and sector-specific challenges (e.g., predictive maintenance, outage management, supply chain resilience, or regulatory compliance). Find the best problem-solution fit and translate customer requirements into innovative solutions that move the needle. • Pre- and Post-Sales Execution: Actively drive the full customer lifecycle. Lead technical discovery and capability demonstrations during the pre-sales cycle, and remain deeply involved post-sale to guide implementation, ensuring agreed value and adoption thresholds are successfully reached. • Hackathons & Prototyping: Think out of the box, have a „can-do“ attitude, and don’t shy away from complex operational problems. Leverage cutting-edge AI technologies to rapidly build creative prototypes in customer hackathons, solving critical pain points specific to power generation, transmission, and O&G operations. • Agentic Process Transformation: Support our customers in achieving real ROI out of AI deployments at scale, enabling a fundamental shift from traditional, rule-based automation to the use of autonomous AI agents empowered by our Celonis Process Intelligence Platform (e.g., intelligent field service routing or autonomous procurement). • Proof Projects: End-to-end execution of business-critical Proof-of-Value projects. This includes architecting and delivering secure, scalable LLM/agent systems with RAG, tools, and guardrails, while seamlessly integrating with enterprise data, identity protocols, and stringent energy compliance frameworks. • Domain & Industry Leadership: Serve as the internal and external technical subject matter expert for the Energy vertical, scaling knowledge across the organization regarding utilities, upstream/downstream oil & gas, and renewable energy processes.

Job Title: Senior GenAI Engineer Job Category: Information Technology Time Type: Full time Minimum Clearance Required to Start: Secret Employee Type: Regular Percentage of Travel Required: Up to 10% Type of Travel: Local * * * The Opportunity: Join our team as a Senior GenAI Engineer supporting Department of War PPBE (Planning, Programming, Budgeting, and Execution) applications. You'll build cutting-edge AI solutions that directly modernize how the DoW plans, programs, budgets, and executes critical defense operations. You’ll work with cross-functional teams to develop AI-enabled features, build intelligent document processing pipelines, and deliver data-driven analytics for mission-critical defense financial systems. While the bulk of this role focuses on generative AI, you will also apply traditional machine learning techniques for forecasting, anomaly detection, and trend analysis on budget and execution data. This role operates across both unclassified and classified environments. Responsibilities: - Design and develop AI-enabled features for PPBE applications using LLMs, GenAI, and agentic AI patterns - Build RAG pipelines over budget justification documents, appropriation language, execution data, and DoD directives - Implement agentic workflows using orchestration frameworks (LangGraph, Agno, Haystack, CrewAI) for multi-step budgeting tasks such as POM construction, BES preparation, and J-Book generation - Develop traditional ML models for budget execution forecasting, obligation rate anomaly detection, and spend trend analysis - Implement prompt engineering strategies and integrate AI/LLM APIs (OpenAI, Anthropic, Bedrock) - Architect full-stack AI features with reliable API integrations, error handling, and graceful degradation - Establish LLM observability (cost, latency, quality) and responsible AI guardrails (hallucination detection, output validation, CUI safeguards) - Maintain full-stack applications (including Web Application development using modern technologies such as React, TypeScript, NodeJS, Python, and .NET) - Address security vulnerabilities and ensure compliance with DoD cybersecurity standards - Participate in code reviews, CI/CD pipelines, and collaborative development workflows - Document technical implementations and stay current with AI and ML developments Qualifications: Required: - Active Secret clearance - Bachelor’s degree in Computer Science, Data Science, Mathematics, or related STEM field. Masters degree preferred. - Masters degree and 12+ years of SDLC experience OR Bachelors and 15+ years of SDLC experience - Security+ Certification - 2+ years experience developing generative AI / LLM-powered applications - Expert-level proficiency in Python; strong JavaScript proficiency - Experience with RESTful APIs and integrating AI/LLM APIs (OpenAI, Anthropic, Bedrock) - Experience with prompt engineering techniques (few-shot, chain-of-thought, system prompts) - Experience with LLM orchestration frameworks such as LangGraph, Agno, CrewAI, or similar - Experience with RAG architectures, agentic patterns, and vector databases - Strong understanding of ML fundamentals (supervised/unsupervised learning, model evaluation, feature engineering, NLP) - Experience with data analysis and ML libraries (pandas, NumPy, scikit-learn, or equivalent) - Experience with containerization (Docker) and at least one major cloud platform (AWS, Azure, or GCP) - Proficiency with Git version control and CI/CD pipelines - Strong written and verbal communication skills Desired: - Experience building predictive models for financial forecasting, anomaly detection, or resource allocation optimization - Experience with vector databases (Chroma, Weaviate, pgvector) and embedding models - Familiarity with LLM observability tools (LangFuse, LangSmith, Weights & Biases) - Understanding of responsible AI concepts: bias mitigation, hallucination detection, safety guardrails - Experience with AWS GovCloud, AWS Bedrock, or Azure OpenAI Service - Working knowledge of Kubernetes, Terraform or other IaC tools, and infrastructure automation - What You Can Expect: A culture of integrity. At CACI, we place character and innovation at the center of everything we do. As a valued team member, you’ll be part of a high-performing group dedicated to our customer’s missions and driven by a higher purpose – to ensure the safety of our nation. An environment of trust. CACI values the unique contributions that every employee brings to our company and our customers - every day. You’ll have the autonomy to take the time you need through a unique flexible time off benefit and have access to robust learning resources to make your ambitions a reality. A focus on continuous growth. Together, we will advance our nation's most critical missions, build on our lengthy track record of business success, and find opportunities to break new ground — in your career and in our legacy. Pay Range: There are a host of factors that can influence final salary including, but not limited to, geographic location, Federal Government contract labor categories and contract wage rates, relevant prior work experience, specific skills and competencies, education, and certifications. Our employees value the flexibility at CACI that allows them to balance quality work and their personal lives. We offer competitive compensation, benefits and learning and development opportunities. Our broad and competitive mix of benefits options is designed to support and protect employees and their families. At CACI, you will receive comprehensive benefits such as; healthcare, wellness, financial, retirement, family support, continuing education, and time off benefits. Since this position can be worked in more than one location, the range shown is the national average for the position. The proposed salary range for this position is: $105,100-$231,100 CACI is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, pregnancy, sexual orientation, age, national origin, disability, status as a protected veteran, or any other protected characteristic.