Bedrock AI Engineer - Production LLM Dev in Finance

Tata Consultancy Services; Malvern (Chester County); On-site; USD 130,000 - 160,000; Full time

Benefits offered by this job

Discretionary Annual Incentive

Medical Coverage

Professional Growth & Training

Job summary

Tata Consultancy Services in the United States seeks a senior AI/ML software engineer to drive Bedrock-based pipelines on high-volume financial document workloads. You will design prompts, build agentic workflows, and replace legacy rules with scalable Bedrock components.

The role requires 10+ years in software engineering with Python, deep AWS expertise, and a track record deploying Foundation Models in production. Expect hands-on coding, mentoring, and cross-team collaboration.

Qualifications

• 10+ years of software engineering experience with Python as your primary language.
• Hands-on experience with Amazon Bedrock — model invocation, Agents, Knowledge Bases, and Guardrails.
• Experience with prompt engineering — designing, versioning, and evaluating prompts in a production context, not just experimentation.
• Familiarity with LLM evaluation patterns: ground truth datasets, accuracy measurement, regression testing for model outputs.
• Strong AWS fundamentals: Lambda, S3, SQS, SNS, EventBridge, CloudWatch, IAM, Secrets Manager.
• Experience with agentic patterns and tool use — building systems where the model calls external APIs as part of a reasoning chain.
• Comfortable working with structured and unstructured document formats (PDF, Excel, DOCX) and document intelligence pipelines (AWS Textract or equivalent).
• AWS ML certification is a plus; a demonstrated track record working with Bedrock and Foundation Models in production carries equal weight.
• Understanding of how to build observable AI systems — logging model inputs/outputs, tracking token costs, detecting accuracy drift in production.

Responsibilities

• Design, build, and optimize Bedrock-powered pipelines replacing custom-trained NLP and rule-based models across multiple production Lambda functions.
• Develop and iterate on prompts, agentic workflows, and tool-use patterns that extract transaction attributes from complex financial documents — PDFs, Excel, Word, and images.
• Implement Bedrock Knowledge Bases to replace hard-coded business rules and fragile per-invocation API calls with managed, queryable reference data.
• Build and maintain an evaluation harness to measure FM extraction accuracy against histori cal ground truth, enforcing accuracy gates before any production promotion.
• Integrate Bedrock Agents with internal APIs using tool-use patterns, replacing legacy direct database queries.
• Participate in parallel-run infrastructure — running old and new systems side by side in TEST, logging divergence, and driving statistical validation before cutover.
• Contribute to team knowledge transfer; this role works closely with the Senior AI Engineer who leads FM and Bedrock capability building across the teams.

Skills

Python

Prompt engineering

LLM evaluation patterns

Observability & logging

Mentoring & leadership

Migration planning

Education

Bachelor of Computer Science

Tools

Amazon Bedrock

AWS Lambda

S3

SQS

SNS

EventBridge

CloudWatch

IAM

Secrets Manager

Bedrock Foundation Models

Textract or equivalent

Job description

Tata Consultancy Services in the United States seeks a senior AI/ML software engineer to drive Bedrock-based pipelines on high-volume financial document workloads. You will design prompts, build agentic workflows, and replace legacy rules with scalable Bedrock components.

The role requires 10+ years in software engineering with Python, deep AWS expertise, and a track record deploying Foundation Models in production. Expect hands-on coding, mentoring, and cross-team collaboration.