Generative & Agentic AI Engineer
About The Position
As an Engineer on the Generative & Agentic AI team, you will play a hands-on role in building, deploying, and operating AI capabilities that power Babel Street’s intelligence applications. You will work closely with senior AI leaders, product teams, and engineers to implement generative and agentic AI solutions that support investigative, analytical, and operational workflows across the platform. This is an execution-focused role for an engineer with strong foundations in machine learning and generative AI who is excited to work on real-world, mission-driven applications. You will contribute directly to LLM and SLM pipelines, retrieval and grounding systems, agent workflows, and AI-enabled features—while learning how to deliver AI that is safe, reliable, cost-efficient, and production-ready. This is a hybrid role to be based out of either our Reston, VA/Washington DC office or our Somerville MA office. Role Focus: This role spans three practical execution areas: Generative AI & Model Development: You will help implement and operate LLM- and SLM-based systems, contributing to prompt development, fine-tuning, evaluation, and inference optimization. You will support retrieval-augmented generation (RAG) pipelines, embeddings, and grounding techniques to ensure AI outputs are accurate, explainable, and aligned with intelligence use cases. Agentic AI & Workflow Automation: You will assist in building and integrating agent-based workflows that automate analytical tasks, connect platform services, and support intelligence applications. This includes implementing agent logic, tool-use patterns, and basic orchestration under the guidance of senior engineers. AI Engineering & Production Delivery: You will help productionize AI capabilities using modern AI SDLC tools and practices, contributing to evaluation, testing, telemetry, and guardrails that reduce hallucinations and ensure safe behavior. You will work within established governance frameworks to ensure AI features are measurable, reliable, and cost-aware. What you will do: Implement and maintain LLM and SLM pipelines, including prompt engineering, inference, and evaluation. Support RAG pipelines, embeddings, and retrieval systems used in intelligence applications. Assist in building agent workflows that automate analytical or operational tasks. Write clean, maintainable code (Python or others) to support AI services and integrations. Contribute to AI evaluation, testing, and hallucination-mitigation techniques. Use AI-assisted development tools (e.g., Copilot, Cursor) to improve development velocity and quality. Collaborate with Product and Engineering teams to integrate AI capabilities into user-facing workflows. Follow established AI governance, safety, and cost-optimization practices.
Requirements
- 5+ years of experience in software engineering, machine learning, or applied AI roles.
- Hands-on experience working with LLMs and/or SLMs, including prompting, inference, or fine-tuning.
- Experience building or contributing to RAG pipelines, embeddings, or retrieval systems.
- Familiarity with agent-based systems or workflow automation (academic, professional, or open-source).
- Strong programming skills in Python; experience with common libraries (PyTorch, TensorFlow, etc.).
- Solid foundation in machine learning concepts (training, evaluation, overfitting, metrics).
- Experience using or contributing to modern AI/ML tooling and workflows (ML pipelines, evaluation scripts, model serving).
- Ability to work in a collaborative, fast-moving, mission-driven environment.
- Bachelor’s degree in Computer Science, Engineering, Data Science, or a related technical field required.
Nice To Haves
- Applying AI to intelligence, investigative, analytical, or risk-related applications.
- Familiarity with vector databases, graph databases, or knowledge graphs.
- Advanced degree is a plus but not required.
Responsibilities
- Implement and maintain LLM and SLM pipelines, including prompt engineering, inference, and evaluation.
- Support RAG pipelines, embeddings, and retrieval systems used in intelligence applications.
- Assist in building agent workflows that automate analytical or operational tasks.
- Write clean, maintainable code (Python or others) to support AI services and integrations.
- Contribute to AI evaluation, testing, and hallucination-mitigation techniques.
- Use AI-assisted development tools (e.g., Copilot, Cursor) to improve development velocity and quality.
- Collaborate with Product and Engineering teams to integrate AI capabilities into user-facing workflows.
- Follow established AI governance, safety, and cost-optimization practices.
Benefits
- The company may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Number of Employees
1-10 employees
