Technical Lead, AI Engineering

Technical Lead, AI Engineering

Sayari is the transparency company providing the public and private sectors with immediate visibility into complex commercial relationships by delivering the largest commercially available collection of corporate and trade data as a dynamic model of global ownership and trade activity. Sayari's solutions harness this model to enable risk resilience, complex investigations, and clear-eyed business decisions. Sayari is headquartered in Washington, D.C., and its solutions are used by thousands of frontline analysts in over 35 countries. Our company culture is defined by a dedication to our mission of using open data to enhance visibility into global commercial and financial networks, a passion for finding novel approaches to complex problems, and an understanding that diverse perspectives create optimal outcomes. We embrace cross-team collaboration, encourage training and learning opportunities, and reward initiative and innovation. If you like working with supportive, high-performing, and curious teams, Sayari is the place for you.

Mirato is now a part of Sayari and is looking for a Technical Lead, AI Engineering. As a Technical Lead at Sayari, you will own the cross-section between classical NLP and modern LLMs. You will design, build, and scale internal AI services—combining spaCy/NLTK and keyword/BOW approaches with prompt-driven LLM agents—backed by robust Python services, ETL/ELT data pipelines, and PostgreSQL. You'll partner closely with our data scientist to productionize models and continuously improve latency, throughput, and quality.

Job Responsibilities

Ship internal AI applications end-to-end: design APIs (FastAPI), write performant async Python, and deliver observability, tests, and CI/CD, including Database design to support those applications.

Own and maintain NLP/LLM pipelines that power internal services (prompt patterns, parameter tuning, fallbacks/guardrails, evaluation, inference).

Develop and scale agents for LLM tasks (tool use, retrieval, routing, self-critique/verification).

Collaborate with the data scientist to implement new capabilities, evaluate model quality, and move prototypes to production.

Skills & Experience

Python expertise: FastAPI, asyncio, ORM (e.g., SQLAlchemy), and hands-on performance work (profiling, async I/O, CPU vs. memory trade-offs).

Classical NLP: spaCy, NLTK, BOW, keyword/regex pipelines; practical text normalization, tokenization, NER, and rule-based extraction.

LLMs: prompt/chain design, parameterization (temperature/top-p/max tokens), patterns (RAG, ReAct, CoT, tool use), and safety/guardrails.

Agents: experience building task-oriented LLM agents and evaluators; fallback strategies and observability for agent behavior.

Pipelines: Python ETL/ELT, workflow orchestration (Airflow/Prefect/Dagster or equivalent).

Databases: PostgreSQL schema design, indexing, query optimization.

Testing: unit/integration/load testing, API contract testing; comfort with test data management and golden datasets.

Collaboration: mentoring, design reviews, structured debugging, and working across functions.

Benefits: Mandatory benefits provided including Public Health Insurance, Statutory Pension, Study Fund, Meal Allowance and other entitlements. Generous time off; we observe all public holidays, and close our office for a winter break (12/24-12/31), in addition to granting 20 vacation days, plus other mandatory paid leave and other entitlements (i.e. Sick time, Travel Expenses, Recreation Pay, etc.). Outstanding compensation package; competitive commissions for revenue roles and quarterly bonuses for non-revenue positions. A strong commitment to diversity, equity, and inclusion. A collaborative and positive culture - your team will be as smart and driven as you. Limitless growth and learning opportunities.