Skip to main content
Loading
loadingbar
Loading, Please wait..!!

AI Engineer (Applied LLM Systems)

  • AI Engineer (Applied LLM Systems) job type Posted on: Oct 26, 2026
  • AI Engineer (Applied LLM Systems) experience level Discernis
  • AI Engineer (Applied LLM Systems) employment type New York City Metropolitan Area, New York
  • AI Engineer (Applied LLM Systems) employment type Onsite
  • AI Engineer (Applied LLM Systems) salary Full-time

Point Apply Here APPLY LATER

Curious about compensation?

Explore the historical salary trends, average pay, and estimated compensation for AI Engineer (Applied LLM Systems) roles in New York.

View Salary Guide →

Job Title :

AI Engineer (Applied LLM Systems)

Job Type :

Full-Time

Job Location :

New York City Metropolitan Area New York United States

Remote :

No

Jobcon Logo Job Description :

About DiscernisDiscernis builds AI driven document intelligence for high stakes legal work. Because our customers handle privileged and regulated matters that most cloud AI cannot touch, we run on premises and in customer controlled environments as well as in the cloud. That makes security, reliability, and reproducibility core product features, not afterthoughts. We work with AmLaw firms and enterprise legal teams where accuracy, explainability, and data control are non negotiable.The RoleYou will lead the design and evolution of the AI systems at the core of our product. Day to day, that means inventing new AI powered workflows that help legal teams understand massive document sets, then making them faster and more reliable, and building the evaluations that tell us we are getting it right. You will reach for whatever technique fits the problem, prompt engineering, agentic orchestration, retrieval, or post-training, and because our customers often cannot send data to external providers, much of this runs on models we host and improve ourselves.What You Will DoDesign and build new AI powered workflows that solve real problems for legal teams, using whatever gets the best result: agentic and multi step orchestration, prompt engineering, retrieval, and post-trainingImprove the quality, reliability, latency, and cost of existing workflows using that same full toolkitOwn and develop our evaluation and benchmarking frameworks so we can measure and improve quality, catch regressions, and know we are moving in the right directionDesign agentic patterns and structured outputs robust enough for complex legal and investigative use casesOwn self hosted model serving and inference optimization across customer deploymentsPost-train and adapt models where that is the right lever, including fine tuning, preference optimization, and domain adaptationWhat You BringExperience building production LLM or ML powered features end to end, with the judgment to know which technique fits which problemHands on experience with agentic or multi step LLM orchestration and tool useBreadth across the modern LLM toolkit: prompt engineering and retrieval, and ideally post-training methods such as fine tuning, DPO, or RLHFExperience designing and running evaluations for LLM systemsHands on experience with self hosted model serving such as vLLM, TGI, or similarStrong Python skills and comfort with concurrent or distributed processingBonus: embedding and vector search pipelines, or retrieval augmented generation at scaleBonus: background in legal tech, document intelligence, or information retrievalTech EnvironmentPython, self hosted inference (vLLM), LLM orchestration and agent frameworks, evaluation toolingApply Here:

Jobcon Logo Position Details

Posted:

Oct 26, 2026

Reference Number:

10440_4437481072

Employment:

Full-time

City:

New York City Metropolitan Area

Job Origin:

APPCAST_CPC

Share this job:

  • linkedin

Jobcon Logo
A job sourcing event
In Dallas Fort Worth
Aug 19, 2017 9am-6pm
All job seekers welcome!

AI Engineer (Applied LLM Systems)    Apply

Click on the below icons to share this job to Linkedin, Twitter!

About DiscernisDiscernis builds AI driven document intelligence for high stakes legal work. Because our customers handle privileged and regulated matters that most cloud AI cannot touch, we run on premises and in customer controlled environments as well as in the cloud. That makes security, reliability, and reproducibility core product features, not afterthoughts. We work with AmLaw firms and enterprise legal teams where accuracy, explainability, and data control are non negotiable.The RoleYou will lead the design and evolution of the AI systems at the core of our product. Day to day, that means inventing new AI powered workflows that help legal teams understand massive document sets, then making them faster and more reliable, and building the evaluations that tell us we are getting it right. You will reach for whatever technique fits the problem, prompt engineering, agentic orchestration, retrieval, or post-training, and because our customers often cannot send data to external providers, much of this runs on models we host and improve ourselves.What You Will DoDesign and build new AI powered workflows that solve real problems for legal teams, using whatever gets the best result: agentic and multi step orchestration, prompt engineering, retrieval, and post-trainingImprove the quality, reliability, latency, and cost of existing workflows using that same full toolkitOwn and develop our evaluation and benchmarking frameworks so we can measure and improve quality, catch regressions, and know we are moving in the right directionDesign agentic patterns and structured outputs robust enough for complex legal and investigative use casesOwn self hosted model serving and inference optimization across customer deploymentsPost-train and adapt models where that is the right lever, including fine tuning, preference optimization, and domain adaptationWhat You BringExperience building production LLM or ML powered features end to end, with the judgment to know which technique fits which problemHands on experience with agentic or multi step LLM orchestration and tool useBreadth across the modern LLM toolkit: prompt engineering and retrieval, and ideally post-training methods such as fine tuning, DPO, or RLHFExperience designing and running evaluations for LLM systemsHands on experience with self hosted model serving such as vLLM, TGI, or similarStrong Python skills and comfort with concurrent or distributed processingBonus: embedding and vector search pipelines, or retrieval augmented generation at scaleBonus: background in legal tech, document intelligence, or information retrievalTech EnvironmentPython, self hosted inference (vLLM), LLM orchestration and agent frameworks, evaluation toolingApply Here:

Loading
Please wait..!!