About the Role
Job Title: AI/ML Software Engineer (LLM, RAG & Automation)
Location: Annapolis, MD (Remote/Occasional Onsite Support as Needed)
Duration: Long-Term Contract (5 Years)
Job Summary
We are seeking an AI/ML Software Engineer to design and build intelligent software solutions that leverage machine learning, large language models (LLMs), and automation techniques. This role focuses on developing scalable systems for chatbot applications, knowledge retrieval, document processing, and workflow automation, while improving both internal operations and user-facing services.
Key Responsibilities
1. System Design & Collaboration
Design and develop AI/ML-driven applications for automation, analytics, and user support
Collaborate with cross-functional teams to define system architecture, workflows, and agent-based solutions
Evaluate and select appropriate approaches (LLM vs non-LLM) based on use cases
Integrate AI/ML solutions into existing enterprise systems and workflows
2. Testing, Evaluation & Optimization
Build and maintain testing and evaluation pipelines for AI systems
Develop unit and integration tests for AI-enabled workflows
Use synthetic data for benchmarking and performance improvement
Optimize models and systems for accuracy, latency, and cost efficiency
3. Deployment & Operations
Deploy AI/ML applications in hybrid cloud environments
Work with containerized environments (Docker) for deployment and scaling
Optimize solutions for limited compute environments (minimal GPU availability)
4. General Responsibilities
Deliver production-grade AI/ML systems aligned with business requirements
Document system architecture, workflows, and technical decisions
Stay current with advancements in AI/ML, LLMs, and related technologies
Core Solution Areas
Chatbot development (internal & external)
Retrieval-Augmented Generation (RAG) and knowledge search systems
Robotic Process Automation (RPA)
Translation and transcription systems
PII detection and redaction solutions
Document analysis and generation
Deep research systems using graph-based retrieval (GraphRAG)
Required Qualifications
Education
Bachelor's degree in Computer Science, Engineering, Data Science, Mathematics, or related field
Experience
3+ years of experience in AI/ML, Data Science, or Applied AI development
3+ years of experience in software engineering or backend development
Technical Skills
AI/ML & Data
Experience with LLMs (API-based and/or local deployment)
RAG systems: embeddings, vector search, re-ranking, graph-based retrieval
Fine-tuning language models or embedding models
Experience with graph databases (e.g., Neo4j)
Strong understanding of NLP (classical + LLM-based techniques)
Programming & Development
Strong proficiency in Python
Experience building APIs, backend services, and data pipelines
Knowledge of SQL and relational databases (e.g., PostgreSQL)
Systems & Tools
Git and version control systems
Docker and containerization
Service-oriented architecture and distributed systems
AI Engineering Practices
Validating AI outputs and mitigating hallucinations
Designing multi-agent or task-based AI systems
Building scalable, production-ready AI pipelines
Additional Technical Knowledge
Hybrid cloud environments and distributed computing
Asynchronous processing, threading, and queue systems
Frontend frameworks (e.g., React) for chatbot interfaces
Microsoft Teams Toolkit (preferred)
Experience with performance-oriented languages (e.g., Rust) is a plus
Key Competencies
Strong problem-solving and analytical skills
Ability to work with complex and evolving datasets
Experience balancing accuracy, performance, and cost in AI systems
Effective collaboration in cross-functional and constrained environments
Work Environment
Remote-first with occasional onsite collaboration
Long-term, innovation-driven project environment
Opportunity to build cutting-edge AI/ML and LLM-based systems at scale
For more details reach at mchoudhary@navitassols.com.