I'm looking for AI Engineering roles (Agentic AI, Workflow automation, Applied AI)

About me: I build production-grade AI systems for high-stakes domains where hallucinations are unacceptable.

Recently, I designed a multi-agent legal AI that:

• Generates IRAC legal memos from raw case facts

• Uses tool-mandatory verification (CourtListener API)

• Enforces zero-trust citations (0% hallucinated cases in testing)

• Runs a 5-agent sequential pipeline (analysis → statutes → cases → damages → strategy)

This is not a chatbot — it's a deterministic research system designed for reliability over fluency.

Looking for: Full-time roles in:

• LLM systems engineering

• AI infrastructure / agent architecture

• Applied AI in high-stakes domains (legal, healthcare, finance)

Skills:

• LLM systems (CrewAI, LangChain, OpenRouter)

• Multi-agent architectures (sequential pipelines, tool grounding)

• Prompt engineering (CoT, adversarial prompting, anti-hallucination)

• API integrations (CourtListener, Tavily, SERP)

• Python, system design, production deployment

See all my AI project in my github profile:

Portfolio : AbrarMuhtasim14 (Abrar Muhtasim) · GitHub