AI/ML Engineer, LLM & Agentic Systems
Overview
You will architect and ship production-grade LLM applications and RAG pipelines in a 10-month contract for a Boston-area client. You will design multi-agent frameworks with LangChain or AutoGen, optimize retrieval with Pinecone or Weaviate, and deploy models on AWS or Azure. You will work with a tight team of engineers, integrating your agents with Kubernetes and Docker. This role demands 80% coding and 20% strategy, with direct ownership of the AI roadmap.
What You'll Do8
- 1Design and deploy scalable RAG systems using LangChain or LlamaIndex, integrating with vector databases like Pinecone or Weaviate.
- 2Build autonomous multi-agent workflows with AutoGen or CrewAI, orchestrating task decomposition and tool use.
- 3Fine-tune large language models on Pytorch or TensorFlow, optimizing for latency and cost.
- 4Ship models to production on AWS or Azure, using Kubernetes and Docker for containerization.
- 5Develop evaluation pipelines for retrieval quality and agent correctness, using tools like RAGAS.
- 6Collaborate with data engineers to ensure data quality and pipeline reliability, using Apache Airflow or Spark.
- 7Debug and optimize inference performance, reducing response times by 30%.
- 8Document architecture decisions and maintain code quality with Git and CI/CD tools.
Requirements8
- 18+ years in software/AI engineering, with 3+ years building production LLM apps.
- 2Hands-on mastery of multi-agent orchestration with LangChain or AutoGen.
- 3Proven experience with RAG pipelines, vector databases, and embedding models.
- 4Strong Python skills, including Pydantic, FastAPI, and asyncio.
- 5Experience deploying models on AWS or Azure, with Kubernetes and Docker.
- 6Familiarity with evaluation metrics for LLM systems, such as ROUGE or BERTScore.
- 7Ability to work onsite in Salem, MA for a 10-month contract.
- 8Authorization to work in the US (Citizen, H-1B, OPT, GC).
Salary Insight
$60 - $70k per year
Location
Required Skills
Similar open positions
Explore active roles that match your skills and interests.
TechniPros, LLC
VerifiedLead Agentic AI Engineer, LLM & LangGraph
Build enterprise-grade AI agents that reason, plan, and execute autonomously. You'll architect scalable applications with LangGraph, RAG, and MCP, integrating cloud AI platforms like AWS Bedrock and Azure AI. You'll lead a team of engineers, shaping the technical roadmap from day one. This role demands deep expertise in LLM orchestration and production deployment.
Saim Technologies
VerifiedLead AI Engineer, Agentic AI Systems
You will own the architecture and delivery of production-grade Agentic AI solutions at scale. You will lead a team of AI engineers, defining technical strategy and driving end-to-end system development. This role stands out for its focus on deploying autonomous agents in real-world enterprise environments, requiring deep expertise in Python, LangChain, and LLM orchestration.
TechniPros, LLC
VerifiedGenerative AI Engineer, LLM & RAG Systems
You will own the design and delivery of GenAI prototypes and workflows at enterprise scale across financial services. You will join the Business Support team, reporting to the AI Engineering lead. You will research emerging AI technologies, build LLM-based solutions, and benchmark models to drive adoption. 3+ years of hands-on Python and GenAI experience is required. This role offers direct collaboration with engineering teams to ship production-ready AI innovations.
Lorven Technologies, Inc.
VerifiedSenior AI Engineer, Multi-Agent Systems (Contract)
You will design end-to-end Agentic AI architectures integrating agent lifecycle frameworks, data infrastructure, orchestration, and enterprise platforms. You will develop and refine AI agents that operate at enterprise scale, collaborating with cross-functional teams to ship production-ready systems. This contract role in Blaine, MN (hybrid) gives you ownership of the agentic layer, from LLM orchestration to RAG pipelines and Kubernetes deployment. You will shape the technical direction and mentor data engineers, making this role distinct for its focus on multi-agent systems in a Fortune 500 environment.
Rapsys Technologies
VerifiedAI/ML Engineer AWS LLM Systems
You will own the design and delivery of AI/ML and LLM-based systems for a high-traffic enterprise platform. You will join a collaborative team of engineers and data scientists in Charlotte, NC, working on mission-critical features. This contract role offers the chance to shape production AI infrastructure from day one. You will build with Python, FastAPI, AWS, and React to drive real business impact.
TATA Consultancy Services Limited
VerifiedAI/LLM Engineer - Agentic Systems & Python
You own the design and build of intelligent agent-based systems that reason, plan, and act autonomously. You join the AI team at TCS in New York, working from the 1633 Broadway office 3 days per week. The stack centers on Python, LangChain, and LLM APIs. You deliver production-ready agents that handle complex workflows. This role demands 8+ years of engineering depth and hands-on LLM expertise.