Junior Applied AI Engineer

SpotDraft; United States; On-site; USD 90,000 - 125,000; Full time

Job summary

SpotDraft is seeking a Junior Applied AI Engineer to help build production AI systems powering our legal‑tech products. You will work with senior engineers to develop distributed AI services that process large volumes of documents, optimize LLM performance, and ensure reliability in a SaaS environment.

Ideal candidates have hands-on experience with LLMs, prompt engineering, and Python, and enjoy collaborating across teams to improve features, reduce costs, and push the boundaries of legal tech.

Qualifications

• Upto 3 years of software/ML engineering experience with exposure to LLM-based systems.
• Experience integrating LLM APIs (GPT-4, Claude, Gemini, or Llama) and prompt engineering.
• Know-how of context engineering — structuring, trimming, and managing what gets passed into the model's context window across a workflow.
• Understanding of agent loops and graphs — how agentic control flow works (e.g. ReAct-style loops, state graphs, conditional branching between steps/tools).
• Hands-on experience building agentic workflows — chaining tool calls, managing state across turns, and handling multi-step reasoning.
• Experience building or contributing to eval systems — writing test cases, scoring outputs, and tracking quality/regression over time.
• Solid Python skills with an understanding of core software engineering practices (testing, version control, code review).
• Foundational understanding of transformer architectures, embeddings, and how LLMs work.
• Some exposure to vector databases and semantic search concepts
• Familiarity with async programming and API frameworks (FastAPI or similar)
• Basic understanding of data structures, algorithms, and complexity
• Comfort working in a fast-paced environment and learning quickly from senior engineers and code reviews.

Responsibilities

• Build AI features using transformer-based architectures for legal document workflows.
• Contribute to agentic systems with ReAct-style flows and tool calling.
• Write and refine prompts and manage prompt libraries and versioning.
• Build retrieval pipelines: chunking, BM25, and dense embeddings.
• Assist in retrieval-grounded generation and context window tuning.
• Work with vector databases to support semantic search features.
• Develop API services that call LLM providers with retry logic, rate limiting, and fallbacks.
• Support inference optimization: caching, batching, and latency/cost monitoring.
• Write production-grade Python code within existing service architectures.
• Develop evaluation scripts and datasets to measure model quality and regression.
• Participate in A/B testing of prompts, models, and configurations.
• ML Ops: CI/CD pipelines, containerization, basic Kubernetes; monitoring dashboards; debugging with logs.

Skills

LLM API integration

Context engineering

Agent loops

Agentic workflows

Eval systems

Python programming

Transformer architectures

Vector databases

Async programming

Data structures & algorithms

Tools

Docker

FastAPI

Kubernetes

AWS

GCP

Azure

LangChain

Weaviate

Job description

About SpotDraft

SpotDraft is on a mission to help legal and business teams move faster, together. Our AI-powered contracting platform is redefining how companies manage contracts, and our story deserves to be told in creative, human, and memorable ways.

Job Summary

SpotDraft is revolutionizing legal operations with AI-powered tools that help legal teams work faster and smarter. Our flagship products leverage cutting-edge LLM technology to automate routine legal work and accelerate contract review.
Sidebar is an AI-powered team of legal assistants that handles routine legal work—from contract analysis and legal research to compliance tracking and drafting SpotDraft. It tackles everything beyond contracts, including policy questions, regulatory compliance, and strategic advice SpotDraft, learning from your organization's knowledge to become a specialized legal co-pilot.
VerifAI is an AI contract review tool that works as a Microsoft Word add-in, helping legal teams review contracts up to 70% fasterwith SpotDraft. It uses generative AI to check contracts against personal or organizational guidelines and answer open-ended questions SpotDraft, automatically flagging deviations and suggesting improvements.

The Role

As a Junior Applied AI Engineer, you'll help build and maintain the production AI systems powering our legal-tech products. Working alongside senior engineers, you'll contribute to distributed AI services that process large volumes of legal documents, support multi-agent architectures, and help optimize LLM performance for accuracy, speed, and cost in our mission-critical SaaS environment.

What You'll Do

Build AI Features

• Implement and iterate on AI features using transformer-based architectures and prompt engineering for legal document workflows (summarization, clause extraction, document comparison, drafting assistance)

• Contribute to agentic systems (ReAct-style flows, tool/function calling, multi-turn reasoning) under the guidance of senior engineers

• Write and refine prompts, and help maintain prompt libraries and versioning

Support RAG & Context Systems

• Help build and maintain retrieval pipelines: chunking strategies, hybrid search (BM25 + dense embeddings), and reranking for legal documents

• Assist in building retrieval-grounded generation pipelines and tuning context window usage

• Work with vector databases (Pinecone, Weaviate, Qdrant, or pgvector) to support semantic search features

Contribute to Infrastructure & Performance

• Help build and maintain API services that call LLM providers (OpenAI, Anthropic, Google Gemini), including retry logic, rate limiting, and fallback handling

• Support inference optimization efforts: caching, batching, and monitoring latency/cost

• Write clean, tested, production-grade Python code within existing service architectures

Support Quality & Reliability

• Help build evaluation scripts and test datasets to measure model output quality (accuracy, hallucination rate, relevance)

• Assist with LLM-as-judge pipelines and human-in-the-loop labeling workflows

• Participate in A/B testing of prompts, models, and configurations

MLOps & Observability

• Support CI/CD pipelines for AI feature deployment (containerization, basic Kubernetes usage)

• Help maintain monitoring dashboards for latency, token usage, error rates, and cost per request

• Assist in debugging production issues using logs, traces, and dashboards

What We're Looking For

Must Have

• Upto 3 years of experience in software/ML engineering, with at least some hands-on exposure to LLM-based systems

• Working experience integrating LLM APIs (GPT-4, Claude, Gemini, or Llama) — prompt engineering, function calling, or basic fine-tuning

• Know-how of context engineering — structuring, trimming, and managing what gets passed into the model's context window across a workflow

• Understanding of agent loops and graphs — how agentic control flow works (e.g. ReAct-style loops, state graphs, conditional branching between steps/tools)

• Hands-on experience building agentic workflows — chaining tool calls, managing state across turns, and handling multi-step reasoning

• Experience building or contributing to eval systems — writing test cases, scoring outputs, and tracking quality/regression over time

• Solid Python skills with an understanding of core software engineering practices (testing, version control, code review)

• Foundational understanding of transformer architectures, embeddings, and how LLMs work

• Some exposure to vector databases and semantic search concepts

• Familiarity with async programming and API frameworks (FastAPI or similar)

• Basic understanding of data structures, algorithms, and complexity

• Comfort working in a fast-paced environment and learning quickly from senior engineers and code reviews

Good to Have

• Exposure to agentic frameworks (LangChain, LangGraph, LlamaIndex, CrewAI, or similar)

• Exposure to text extraction and text wrangling in current/prior work (parsing PDFs, OCR output cleanup, handling messy or unstructured text)

• Experience with Docker and basic CI/CD pipelines

• Familiarity with cloud platforms (AWS, GCP, or Azure)

• Any experience with evaluation frameworks, synthetic test data, or A/B testing for ML systems

• Interest in or coursework related to document/multi-modal AI (OCR, layout analysis, vision-language models)

• A personal project, hackathon, or open-source contribution involving LLMs or RAG systems

Growth Path

This role is designed to grow into a mid-level/Applied AI Engineer position, with mentorship from senior team members on distributed systems design, advanced RAG architecture, and large-scale inference optimization.

Why SpotDraft?

• Brilliant teammates—Work with some of the sharpest minds in legal tech.

• Expand your network—Interact with top founders, investors, and industry leaders.

• Real impact—Take ownership of projects and see your work in action.

• Big goals, bold moves—We trust you to deliver, innovate, and push boundaries.

Our Core Values

• Our business is to delight Customers

• Be Transparent. Be Direct

• Be Audacious

• Outcomes over everything else

• Elevate each other

• Be Passionate. Take Ownership.

• Be 1% better every day

All candidates’ personal data shared during the recruitment process will be handled with utmost confidentiality and used solely for hiring purposes, in line with applicable data protection regulations.

*SpotDraft is an equal-opportunity employer. Candidates will not be discriminated against based on race, ethnicity, color, religion, caste, sex, gender identity, sexual orientation, national origin, veteran, or disability status