Distyl

9 months ago

Applied AI Researcher, Post-Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 14 hours agoStatus: Live

Job Summary

Drive post-training research to align foundation models with real-world enterprise needs. You’ll refine supervised fine-tuning, preference optimization, and continual adaptation, enabling safe, scalable deployment of GenAI solutions across industries while collaborating with enterprise teams and contributing to measurable impact.

Location: San Francisco, New York

Workplace: Hybrid

Employment Type: Full time

Job Function: Research & Scientific (R&D)

Key Responsibilities

•Post-Training: adapt foundation models to real-world performance and alignment requirements; develop and evaluate techniques such as supervised fine-tuning, preference optimization (DPO, RLHF, RLAIF), and continual adaptation to align models with Distyl’s enterprise systems; bridge raw model capability with trustworthy, contextually aligned system behavior.
•Post-Training: investigate methods for aligning large models with human and system-level objectives; explore trade-offs between generalization and specialization, data efficiency and robustness, capability and controllability to inform safe, effective, and scalable use of foundation models across industries.

Pay and Benefits

Equity and Bonus:Equity

Perks:MedicalDentalVision401kEquity

Key Requirements

•Deep understanding of post-training techniques, including supervised fine-tuning, RLHF/DPO, LoRA/PEFT, and instruction-tuning pipelines.

Experience:Enterprise AIGenAIResearch

Skills:ResearchProblem-solvingCommunication

Tech Stack:LoRAPEFTSupervised fine-tuningRLHFDPOInstruction-tuningReActGraph-of-thoughtsData curation

Company Brief

Distyl

Builds enterprise-grade AI systems and integration services (Distillery) to help Fortune 500 companies become AI-native, delivering measurable operational impact across healthcare, telecom, manufacturing, and finance.

Industry: AI & Machine Learning

Company Size: Medium (51 to 250 employees)

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series B

Headquarters: San Francisco, United States

Founded: 2022

Website LinkedIn Glassdoor

Loading job details...

Preparing the role view and application actions.

Distyl

9 months ago

Applied AI Researcher, Post-Training

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 14 hours agoStatus: Live

Job Summary

Location: San Francisco, New York

Workplace: Hybrid

Employment Type: Full time

Job Function: Research & Scientific (R&D)

Key Responsibilities

•Post-Training: adapt foundation models to real-world performance and alignment requirements; develop and evaluate techniques such as supervised fine-tuning, preference optimization (DPO, RLHF, RLAIF), and continual adaptation to align models with Distyl’s enterprise systems; bridge raw model capability with trustworthy, contextually aligned system behavior.
•Post-Training: investigate methods for aligning large models with human and system-level objectives; explore trade-offs between generalization and specialization, data efficiency and robustness, capability and controllability to inform safe, effective, and scalable use of foundation models across industries.

Pay and Benefits

Equity and Bonus:Equity

Perks:MedicalDentalVision401kEquity

Key Requirements

•Deep understanding of post-training techniques, including supervised fine-tuning, RLHF/DPO, LoRA/PEFT, and instruction-tuning pipelines.

Experience:Enterprise AIGenAIResearch

Skills:ResearchProblem-solvingCommunication

Tech Stack:LoRAPEFTSupervised fine-tuningRLHFDPOInstruction-tuningReActGraph-of-thoughtsData curation

Company Brief

Distyl

Industry: AI & Machine Learning

Company Size: Medium (51 to 250 employees)

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series B

Headquarters: San Francisco, United States

Founded: 2022

Website LinkedIn Glassdoor