Job Description

Location - Dallas, TX I South Carolina 

Role Level Senior / Lead Engineer

Responsibility Brings in the required expertise to build context-engineered prompts and skills, plus validation — that turns deterministic findings into high-quality, defensible dispositions.

Role Purpose

Design context-engineered prompts, reasoning skills, and validation logic on AWS Bedrock that convert deterministic scan/graph findings into high-quality, defensible migration and remediation dispositions.

Role Summary

· Owns prompt and reasoning-skill design for turning raw findings into recommendations, built on Bedrock.

· Builds validation/evaluation logic (hallucination mitigation, confidence scoring) so every LLM-generated disposition can be defended and traced back to evidence.

· Works closely with the Graph/RAG Engineer to consume graph outputs as reasoning context.

· Focuses on reasoning quality and defensibility — not the underlying graph/RAG infrastructure itself.

Key Responsibilities

· Design context-engineered prompts and reusable "skills" on Bedrock for dispositioning, impact analysis, and remediation recommendations.

· Build evaluation and validation frameworks (e.g., LangSmith, TruLens, RAGAS-style approaches) that check LLM outputs against deterministic findings for accuracy and defensibility.

· Convert deterministic (rule-based/graph) findings into natural-language, evidence-backed dispositions engineers can act on.

· Identify and reduce hallucination, low-confidence, or unsupported recommendations.

· Support ID de-collision reasoning — distinguishing true ID collisions from co-mingled data at the table level.

· Iterate prompt/skill design across scan rounds as new patterns and edge cases emerge.

Required Skills

· Amazon Bedrock (mandatory — Claude/Titan models, Bedrock Agents, Bedrock Knowledge Bases)

· Prompt engineering and context engineering

· LLM reasoning and agentic reasoning design (LangGraph, CrewAI, or equivalent)

· Output validation and evaluation frameworks (LangSmith, TruLens, RAGAS or similar)

· Working with deterministic + probabilistic hybrid systems

Relevant Experience

· 6+ years in AI/ML engineering with 2+ years focused on LLM prompt/context engineering on AWS Bedrock specifically.

· Experience converting rule-based or graph-based findings into LLM-assisted recommendations.

· Familiarity with hallucination mitigation, confidence scoring, and human-in-the-loop review design.

· Financial services domain exposure is a plus but not mandatory for this role.

Expected Deliverables / Work Products

· Context-engineered prompt/skill library (Bedrock-based)

· LLM validation and confidence-scoring framework

· Disposition quality audit reports

· Reasoning workflow documentation