Software Development Engineer II, Generative AI

Archer; Jersey City (NJ); On-site; USD 140,000 - 190,000; Full time

Job summary

Archer, in collaboration with Verisk, is seeking an experienced software engineer to build GenAI systems end-to-end. You will work from experimentation to production deployment, focusing on reliability, observability, and iteration with senior engineers and product leadership.

Responsibilities include building production-grade GenAI features, implementing RAG and prompt engineering, writing clean Python, and developing monitoring pipelines to ensure grounded and trustworthy outputs.

Qualifications

• 3+ years in software engineering, data science, or ML.
• 1+ years building GenAI/LLM features in production.
• Strong Python and AI/ML frameworks and tooling.
• Understanding of LLMs, embeddings, RAG, prompt engineering, context engineering.
• Experience with cloud-native architectures and deploying scalable apps.
• Knowledge of GenAI evaluation, testing, monitoring, and responsible AI.
• Autonomy, problem solving, and clear communication.
• Bachelor's degree in CS/SE/ML or related field.

Responsibilities

• Build features and components for production-grade GenAI products with quality and performance.
• Implement and iterate on LLM-based solutions, including RAG, prompt engineering, context engineering, and agentic workflows.
• Write clean, well-tested Python code and contribute to the broader codebase and infra.
• Help build evaluation and monitoring pipelines to measure GenAI output quality and reliability.
• Work with foundation models and GenAI tooling, evaluating tradeoffs under guidance.
• Collaborate with Product Owners to translate requirements into technical solutions.
• Participate in code reviews, design discussions, and engineering best practices.
• Debug and resolve issues across the stack, escalating to senior engineers as needed.
• (SDE II) Own medium-complexity features end-to-end and mentor SDE I engineers.

Skills

Python

GenAI

LLMs

RAG

Cloud-native

Code reviews

Education

Bachelor's degree in CS/SE/ML

Tools

PyTorch

LangChain

Kubernetes

Docker

Job description

Archer is collaborating with Verisk to connect them with exceptional professionals for this role.

Description

This is a hands‑on engineering role for someone who wants to build real GenAI systems — not prototypes. You’ll work across the full lifecycle, from experimentation and prompt/RAG design through production deployment, observability, and iteration, partnering closely with senior engineers, product owners, and technical leadership.

Responsibilities

• Build features and components for production-grade GenAI products, with a focus on quality, reliability, and performance.
• Implement and iterate on LLM-based solutions, including retrieval-augmented generation (RAG), prompt engineering, context Engineering, Loop Engineering and agentic workflows.
• Write clean, well-tested, maintainable Python code and contribute to the broader codebase and infrastructure.
• Help build evaluation and monitoring pipelines to measure output quality, groundedness, and reliability of GenAI features.
• Work with foundation models and GenAI frameworks/tooling, evaluating tradeoffs between approaches under guidance from senior engineers.
• Collaborate with Product Owners and cross-functional stakeholders to translate requirements into working technical solutions.
• Participate in code reviews, design discussions, and engineering best practices across the GenAI development lifecycle.
• Debug and resolve technical issues across the stack, escalating and collaborating with senior team members on complex problems.
• (SDE II) Take ownership of medium-complexity features end-to-end, mentor SDE I engineers, and contribute to architecture and design decisions for GenAI components.

Qualifications

• 3+ years of industry experience in software engineering, data science, or machine learning.
• 1+ years of hands‑on experience building GenAI/LLM-based features or applications, ideally in a production setting.
• Strong Python skills and experience with modern AI/ML and GenAI frameworks and tooling.
• Working understanding of LLMs, embeddings, RAG, prompt engineering, context Engineering, and GenAI architecture patterns.
• Experience with cloud-native architectures and deploying scalable applications to production.
• Understanding of GenAI evaluation, testing, monitoring, and responsible AI practices.
• Ability to work with moderate autonomy, break down ambiguous problems, and communicate technical tradeoffs clearly.
• Genuine curiosity and enthusiasm for learning new technologies, tools, and techniques in a fast-moving field.
• Bachelor's degree in Computer Science, Software Engineering, Machine Learning, Data Science, or a related technical field.

Additional Qualifications

• knowledge on fine‑tuning or adapting LLMs (e.g., SFT, LoRA/PEFT, instruction tuning), including preparing training datasets or evaluating fine‑tuned models against baselines is a plus.
• Experience with agentic AI patterns or multi‑step LLM workflows is a plus.