Applied AI Engineer: Production LLMs for Energy Ops

Luxoft; California; Hybrid; USD 140,000 - 190,000; Full time

Job summary

Luxoft in California is seeking an applied AI engineer to build AI features with real, measurable benefit for an energy solutions platform. You will ship LLM-powered capabilities, manage data onboarding, and drive evaluation, monitoring, and performance improvements across our stack (Ruby on Rails, Node.js/TypeScript, Python, PostgreSQL, Snowflake, AWS).

The role emphasizes collaboration with product teams, design of retrieval/RAG pipelines, and scalable AI workflows with CI/CD and enterprise

Qualifications

• Shipped LLM-based features or agents to production.
• Production experience in Python or Node.js/TypeScript.
• Experience building with LLMs: prompt design, structured outputs, retrieval/RAG and agent orchestration.
• Ability to evaluate AI systems with representative data, automated graders, and monitoring.
• Experience with AWS or other enterprise cloud AI services; Bedrock preferred.
• Strong English and communication skills.

Responsibilities

• Collaborate with product teams to define high-value AI use cases and success criteria.
• Design, build and ship LLM-powered features and agents from prototype to production; enable client data onboarding.
• Own retrieval and RAG over data, plus evals, monitoring and cost/latency improvements.
• Develop scalable AI workflows, CI/CD integration, and improve customer-facing AI features.

Skills

LLM-based features production

Python

Node.js/TypeScript

Prompt design

Tool design

Retrieval/RAG

Agent orchestration

AI system evaluation

CI/CD

English communication

Tools

MCPSQL

Snowflake

Terraform

AWS Bedrock

Job description

Project description

Our client is an energy solutions provider. Our AI-enabled platform supports operations, tracking and decision-making to optimize large-scale renewable and traditional energy portfolios. We're delivering a key client MVP in February 2027, and the project continues into 2028. Our stack: Ruby on Rails, Node.js/TypeScript and Python services, PostgreSQL, Snowflake and AWS. We're looking for an applied AI engineer to build AI with real, measurable benefit across our operations and products.

Responsibilities

• Work closely with product teams to help define and execute technical criteriaFind high-value uses for AI and define how success is measuredDesign, build and ship LLM-powered features and agents from prototype to production, such as automating client data onboardingOwn retrieval and RAG over our data, building on the foundation our data engineers prepareBuild evals and monitoring that track quality, cost and latency, and improve systems based on the resultsHelp refine our customer-facing AI features

SKILLS

Must have

• Mid-to-senior software engineer who has shipped LLM-based features or agents to production, not only prototypesProduction experience in Python (preferred) or Node.js/TypeScriptBuilding with LLMs: prompt and tool design, structured outputs, retrieval/RAG and agent orchestrationEvaluating AI systems: eval sets built from representative data, automated graders, human review and production monitoringAWS or another enterprise cloud platform, including its AI services (AWS Bedrock preferred)AI-native development: daily use of agentic AI coding tools, and experience scaling shared AI workflows across a team and into the development lifecycle, including CI/CDStrong English and communication skills

Nice to have

Agent tool protocols such as MCPSQL and cloud warehouse data (Snowflake preferred)Infrastructure as code (e.g. Terraform)Exposure to energy, utilities or sustainability data