AI Engineer – Cloud

This is a fully remote position, open to applicants in United States.

📋 Description

• Create, develop, and sustain AI systems that convert customer interactions and uploaded documents into detailed, verifiable cost estimates.

• Construct and manage LangGraph agents, including ReAct retrieval sub-agents, custom middleware, Pydantic-typed graph state, and streaming flows.

• Take ownership of retrieval quality from start to finish through agentic retrieval, collection routing, LLM-driven metadata filters and similarity thresholds, query rewriting, semantic chunking, and citation tracking.

• Incorporate AWS Bedrock, OpenAI, and self-hosted vLLM behind a unified interface.

• Develop and oversee platform API services, relational and domain-knowledge data stores, vector stores, and AI workflow observability/tracing.

• Establish the technical direction for the AI workstream.

• Evaluate designs and code, mentor engineers, and collaborate with product stakeholders.

• Analyze production AI behavior and implement measurable improvements in accuracy, latency, cost, reliability, and grounding.

• Fulfill roadmap commitments and navigate technical and roadmap trade-offs.

⛳️ Requirements

• A Bachelor's degree in Computer Science, Software Engineering, Data Science, or Mathematics.

• At least 6 years of progressive experience in software engineering.

• 1+ years of experience in building production LLM-powered or machine-learning systems, which include agents, RAG, or prompt/evaluation pipelines.

• Proven track record in a fast-paced work environment.

• Availability to overlap with U.S./Eastern-Time business hours for client meetings.

• Expert-level software engineering skills in production environments.

• Proficiency in developing LLM-powered systems, agents/orchestration, retrieval-augmented generation, and prompt/evaluation pipelines.

• Proficient in utilizing AI development tools.

• In-depth knowledge of retrieval and grounding, embeddings and vector search, multi-model integration, and cost/latency optimization.

• Familiarity with the cost-estimation / Work Breakdown Structure domain, or the ability to quickly grasp complex subjects.

• Capability to analyze intricate, non-deterministic AI behavior from production traces and deliver scalable, well-tested solutions under time constraints.

• Outstanding ability to convey technical and model-behavior concepts clearly to non-technical and client stakeholders.

• Confidence in participating in live U.S./ET client meetings.

• Proven ability to make critical, time-sensitive decisions with limited information.

• High level of ownership, motivation, and a proactive approach.

• Strong leadership skills.

• A desirable master's degree in Computer Science, Machine Learning, or AI.

• Relevant cloud or machine-learning certification is a plus.

• Optional experience with self-hosted model inference, observability and tracing tools, clean layered service architecture, internal AI tooling/automation, cloud platforms, agent-reliability patterns, document ingestion and processing, evaluation/benchmark frameworks, U.S.-based clients, mentoring, design reviews, technical direction, and AI roadmap trade-offs.

🏝️ Benefits

• Flexible working arrangements.

• Support for long-term development.

• A collaborative, trustworthy, quality-driven, and systems-focused work environment.

• Autonomy with accountability and influence over architecture, technical direction, and standards.