Middle Python Engineer with AI Expertise IRC305232

Description

We are looking for a hands-on Senior AI Engineer who can take an AI use case from technical design through implementation and integration into a production environment.

The ideal candidate combines strong Python/software engineering skills with practical experience building LLM and GenAI solutions, and is comfortable working in an enterprise environment with complex business and technical requirements.

Requirements

• 3+ years of software engineering experience with Python, including 1+ year building LLM-powered features or agents.
• Strong production-grade Python: async programming, Pydantic data modeling, pytest, dependency management, code review discipline.
• Hands-on experience with LLM provider APIs (Amazon Bedrock preferred; Anthropic/OpenAI acceptable): streaming, tool use, structured outputs, prompt caching, token accounting.
• Hands-on experience building agents with Strands Agents or LangGraph (or equivalent): agent loop, tool registration, session/state handling, structured output enforcement.
• Working knowledge of core patterns: deterministic workflows vs autonomous loops, map-reduce summarization, routing, evaluator-optimizer (critic) loops.
• Experience designing and implementing agent tools against application APIs, including MCP (Model Context Protocol) or comparable tool-integration standards.
• Solid prompt engineering: system prompt structure, context budgeting, data representation for token efficiency, positioning against lost-in-the-middle effects.
• Experience enforcing schema-validated structured outputs and handling parse/validation failures as designed-for cases, not exceptions.
• Experience building evals: golden datasets, programmatic graders (schema, coverage, totals), LLM-as-judge with rubrics, pass-rate measurement over multiple runs.
• Experience implementing guardrails: input/output validation, iteration/token/cost budgets, treating third-party document text as untrusted input, honest-gap outputs (no plausible filler).
• Experience instrumenting agents with tracing (OpenTelemetry), token/cost/latency logging per run and step, and debugging production traces.
• Working experience with AWS serverless stacks (Lambda, IAM, CloudWatch, SQS), Docker/containers, and CI/CD pipelines.
• Experience integrating with relational data models via APIs, deterministic keyed retrieval, and content-hash-based change detection.
• Ability to work with domain experts to turn business rules into prompts, rubrics, and eval cases; clear written communication.

  #LI-2KK #LI-Remote

Job responsibilities

• Implement agents end-to-end in Python with Strands Agents/LangGraph: prompts, tools, orchestration logic, structured outputs, state persistence.
• Design and implement MCP tool contracts against application APIs; keep tools read-only and least-privilege by default.
• Maintain externalized, versioned prompts and configuration; ensure no prompt change ships without an eval run.
• Build and extend eval suites: golden datasets, programmatic graders, LLM-as-judge rubrics; measure pass rates across repeated runs.
• Implement guardrails and failure handling: schema validation, loop/token/cost budgets, retries, checkpointed resumption, honest degraded outputs.
• Instrument tracing, token/cost/latency accounting per run, step, and tenant; debug production traces.
• Maintain automated test coverage for tools, pipelines, and contracts; contribute to CI/CD for agent deployments.
• Ship changes through staged rollout (shadow mode, pilot cohorts) and monitor results against the incumbent.
• Work with domain experts to translate business rules into prompts, rubrics, and eval cases.
• Share knowledge through documentation and internal sessions; support onboarding of new team members.

What we offer

Empowering Projects: With 500+ clients spanning diverse industries and domains, we provide an exciting opportunity to contribute to groundbreaking projects that leverage cutting-edge technologies. As a team, we engineer digital products that positively impact people’s lives.

Empowering Growth: We foster a culture of continuous learning and professional development. Our dedication is to provide timely and comprehensive assistance for every consultant through our dedicated Learning & Development team, ensuring their continuous growth and success.

DE&I Matters: At GlobalLogic, we deeply value and embrace diversity. We are dedicated to providing equal opportunities for all individuals, fostering an inclusive and empowering work environment.

Career Development: Our corporate culture places a strong emphasis on career development, offering abundant opportunities for growth. Regular interactions with our teams ensure their engagement, motivation, and recognition. We empower our team members to pursue their career goals with confidence and enthusiasm.

Comprehensive Benefits: In addition to equitable compensation, we provide a comprehensive benefits package that prioritizes the overall well-being of our consultants. We genuinely care about their health and strive to create a positive work environment.

Flexible Opportunities: At GlobalLogic, we prioritize work-life balance by offering flexible opportunities tailored to your lifestyle. Explore relocation and rotation options for diverse cultural and professional experiences in different countries with our company.

About GlobalLogic

GlobalLogic, a Hitachi Group Company, is a trusted digital engineering partner to the world’s largest and most forward-thinking companies. Since 2000, we’ve been at the forefront of the digital revolution – helping create some of the most innovative and widely used digital products and experiences. Today we continue to collaborate with clients in transforming businesses and redefining industries through intelligent products, platforms, and services.