Senior AI Engineer, LLM & Agentic Systems
Overview
You will own and evolve the intelligence engine powering Brellium's real-time medical review platform, transforming raw session data into clinically structured outputs at massive scale. You will design and improve LLM-powered pipelines and agent architectures, build robust evaluation frameworks, and optimize for latency, cost, and reliability across high daily volume. Working with backend and product teams, you will ship production-grade AI systems that impact patient care across 250,000+ providers. This role offers the chance to tackle high-stakes clinical challenges with direct feedback loops and meaningful ownership in a Series A company backed by top-tier investors.
What You'll Do6
- 1Design and improve LLM-powered pipelines and agent architectures to handle high daily volumes with accuracy and efficiency.
- 2Build robust evaluation and benchmarking frameworks to measure output quality and regression, incorporating RAG and tool-use strategies.
- 3Optimize for latency, cost, determinism, and output quality across production systems, focusing on structured extraction and function calling.
- 4Ship production-grade AI systems, integrating them into the core platform alongside backend and product teams.
- 5Lead the evolution of the intelligence engine, implementing retrieval-augmented generation and advanced agentic patterns.
- 6Collaborate with cross-functional teams to align AI capabilities with clinical and compliance requirements.
Requirements5
- 15+ years of professional software engineering experience.
- 2Hands-on experience building and shipping LLM-powered applications in production.
- 3Deep familiarity with LLM concepts: prompt engineering, structured extraction, tool calling, RAG, and evaluation frameworks.
- 4Experience with AWS or comparable cloud infrastructure for AI workloads.
- 5Strong software engineering fundamentals, writing clean, maintainable systems.
Salary Insight
$230 - $300k per year
Location
Required Skills
Similar open positions
Explore active roles that match your skills and interests.
Brellium
VerifiedSenior Product Engineer, AI Healthcare
You will own product features from concept to production at Brellium, an AI-powered platform serving 250,000+ providers across all 50 states. You will work with Python, AWS, and modern LLM integration to build the first real-time medical review platform. Your work will directly reduce clinical and compliance risks that affect 1 in 20 U.S. patients annually. This role sits at the intersection of engineering, product, and users, turning ambiguous problems into shipped product.
Esvee Technologies Inc
VerifiedAI Engineer
You will own the design and deployment of production AI systems, specifically focusing on NLP and LLMs within a regulated environment. You will join a team of engineers and data scientists, building on a successful track record of delivering AI solutions. Your work will directly impact the firm's compliance and operational efficiency, requiring close collaboration with product and legal teams.
Wise Skulls Corp.
VerifiedAI Engineer (LLM Agents & Data Engineering)
Lead design and delivery of AI solutions that scale across multiple platforms. Own the end-to-end pipeline from concept to production while driving innovation in large language models. This role shapes how our systems learn and adapt.
Ambiencehealthcare
VerifiedSenior Machine Learning Engineer Ambience Healthcare
Lead development of trustworthy AI evaluation systems and production model behavior at Ambience. Own end-to-end AI systems across models data and infrastructure. Drive measurable improvements in LLM and agentic platforms.
QUANTUM TECHNOLOGIES LLC
VerifiedAI/ML Engineer, LLM & Agentic Systems
You will architect and ship production-grade LLM applications and RAG pipelines in a 10-month contract for a Boston-area client. You will design multi-agent frameworks with LangChain or AutoGen, optimize retrieval with Pinecone or Weaviate, and deploy models on AWS or Azure. You will work with a tight team of engineers, integrating your agents with Kubernetes and Docker. This role demands 80% coding and 20% strategy, with direct ownership of the AI roadmap.
PRIMUS Global Services Inc.
VerifiedAI Engineer, Python FastAPI & LLM Systems
Own the design and deployment of an AI-powered support bot for Hypercare query resolution, processing thousands of enterprise queries daily. You will build RAG pipelines, Agentic AI Workflows, and integrate Large Language Models into production. Work with Python and FastAPI in an onsite Sunnyvale, CA team. This role stands out for its focus on agentic systems and knowledge assist, requiring deep technical ownership from day one.