Senior AI Engineer

Mitratech is looking for a Senior AI Engineer to design, build, and operate intelligent agent systems end-to-end on an AWS-native GenAI platform. This role spans engineering delivery and stable operations, with hands-on work across agent services, evaluation, and reliability for internal tooling, customer-facing experiences, and workflow automation. The position is remote and offers a salary range of USD 170,000 to 190,000 per year.

What you’ll build

You will own LLM-powered agents end-to-end on Amazon Bedrock, using frameworks and tooling such as LangChain and LangGraph, alongside the langchain-aws, langchain-anthropic, and langchain-core stack. Your work includes defining agent workflows and RAG architectures for team-level reuse, and ensuring that agent services remain reliable through production operations.

Responsibilities

• Design and own LLM-powered agents end-to-end for internal tooling, customer-facing features, and workflow automation on Bedrock using LangChain/LangGraph and the langchain-aws / langchain-anthropic / langchain-core stack
• Design agent workflows and RAG architectures for team-level use, influencing design decisions beyond your individual services
• Build and operate MCP servers that expose company data and services as structured tools for AI models
• Define testing, reliability, and operational practices for your areas, and own delivery and on-call quality for major services
• Stand up evaluation pipelines using Langfuse and eval harnesses, implement prompt-versioning practices, and use results to improve reliability and cost/quality
• Lead design reviews, mentor engineers, and drive improvements in engineering practice
• Collaborate with product, data, and platform teams to scope and deliver agent-based solutions while applying platform patterns and governance hooks

Requirements

• 5+ years of software engineering experience, including multiple years building and operating LLM or AI agent systems in production
• Expert-level Python and service development (async, FastAPI, Pydantic v2), with a history of owning services end-to-end
• Deep GenAI/LLM application experience, including RAG architectures and agent workflows (ideally with Claude via Amazon Bedrock or the Anthropic API)
• Strong AWS engineering skills across Bedrock, Lambda, ECS, API Gateway, and related services
• Hands-on experience with LangChain/LangGraph and MCP (building and operating tool/resource servers)
• Experience with Terraform / IaC and containerized delivery through CI/CD
• Data-layer experience with Redis, Snowflake, DynamoDB, and Postgres/Aurora using async SQLAlchemy
• Identity and application security fundamentals including JWT/OAuth and secrets management
• Production observability and LLM evaluation experience, including tracing and eval metrics such as latency/cost/quality
• Demonstrated ability to mentor engineers, lead design reviews, and set engineering practices

Benefits

• Health, Dental & Vision Insurance
• 401(k) + Employer Match
• Open PTO + 11 Paid Holidays + 4 Annual Paid Global Wellness Days Off
• STD, LTD & Group Life Insurance
• Paid Parental Leave
• Pet Insurance
• FSA & HSA Options
• Employee Assistance Program
• Remote Work
• Career Advancement & Professional Development Opportunities
• Employee Recognition
• LinkedIn Learning Platform

Technologies you’ll work with

AWS-native GenAI platform, Amazon Bedrock, LangChain, LangGraph, langchain-aws, langchain-anthropic, langchain-core, FastAPI, Terraform, MCP, Langfuse, Python, Pydantic v2, async, Lambda, ECS, API Gateway, CI/CD, Redis, Snowflake, DynamoDB, Postgres/Aurora, async SQLAlchemy, JWT, OAuth, secrets management, Claude, Anthropic API, tracing, evals, latency/cost/quality metrics.